PAM-4 Transmission at 1550 nm Using Photonic Reservoir Computing Post-Processing

The efficacy of data decoding in contemporary ultrafast fiber transmission systems is greatly determined by the capabilities of the signal processing tools that are used. The received signal must not exceed a certain level of complexity, beyond which the applied signal processing solutions become insufficient or slow. Moreover, the required signal-to-noise ratio (SNR) of the received signal can be challenging, especially when adopting modulation formats with multi-level encoding. Lately, photonic reservoir computing (RC)–a hardware machine learning technique with recurrent connectivity–has been proposed as a post-processing tool that deals with deterministic distortions from fiber transmission. Here, we show that RC post-processing is remarkably efficient for multilevel encoding and for the use of very high launched optical peak power for fiber transmission up to 14 dBm. Higher power levels provide the desired high SNR values at the receiver end, at the expense of a complex nonlinear transformation of the transmission signal. Our demonstration evaluates a direct fiber communication link with 4-level pulse amplitude modulation (PAM-4) encoding and direct detection, without including optical amplification, dispersion compensation, pulse shaping or other digital signal processing (DSP) techniques. By applying RC post-processing on the distorted signal, we numerically estimate fiber transmission distances of 27 km at 56 Gb/s and of 5.5 km at 112 Gb/s data encoding rates, while fulfilling the hard-decision forward error correction (HD-FEC) bit-error-rate (BER) limit for data recovery. In an experimental equivalent demonstration of our photonic reservoir, the achieved distances are 21 and 4.6 km, respectively.

[1]  Oskars Ozolins,et al.  High Speed PAM-8 Optical Interconnects with Digital Equalization Based on Neural Network , 2016, 2016 Asia Communications and Photonics Conference (ACP).

[2]  P. Winzer,et al.  Capacity Limits of Optical Fiber Networks , 2010, Journal of Lightwave Technology.

[3]  Daniel Brunner,et al.  Conditions for reservoir computing performance using semiconductor lasers with delayed optical feedback. , 2017, Optics express.

[4]  Nicklas Eiselt,et al.  Direct detection solutions for 100G and beyond , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[5]  D. C. Agrawal.  Fibre Optic Communication , 2005 .

[6]  L Pesquera,et al.  Photonic information processing beyond Turing: an optoelectronic implementation of reservoir computing. , 2012, Optics express.

[7]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[8]  Serge Massar,et al.  High performance photonic reservoir computer based on a coherently driven passive cavity , 2015, ArXiv.

[9]  Chia-Chien Wei,et al.  Convolutional Neural Network based Nonlinear Classifier for 112-Gbps High Speed Optical Link , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[10]  Laurent Larger,et al.  High-Speed Photonic Reservoir Computing Using a Time-Delay-Based Architecture: Million Words per Second Classification , 2017 .

[11]  Ivan B. Djordjevic,et al.  A Survey on FEC Codes for 100 G and Beyond Optical Networks , 2016, IEEE Communications Surveys & Tutorials.

[12]  Lei Deng,et al.  Digital chromatic dispersion pre-management enabled single-lane 112  Gb/s PAM-4 signal transmission over 80  km SSMF. , 2018, Optics letters.

[13]  B. Eggleton,et al.  Fiber nonlinearity-induced penalty reduction in CO-OFDM by ANN-based nonlinear equalization. , 2015, Optics letters.

[14]  Benjamin Schrauwen,et al.  Optoelectronic Reservoir Computing , 2011, Scientific Reports.

[15]  Darko Zibar,et al.  Machine Learning Techniques for Optical Performance Monitoring From Directly Detected PDM-QAM Signals , 2017, Journal of Lightwave Technology.

[16]  Miguel C. Soriano,et al.  Improving detection in optical communications using all-optical reservoir computing , 2017, 2017 Conference on Lasers and Electro-Optics Europe & European Quantum Electronics Conference (CLEO/Europe-EQEC).

[17]  Geert Morthier,et al.  Experimental demonstration of reservoir computing on a silicon photonics chip , 2014, Nature Communications.

[18]  Junji Ohtsubo,et al.  Semiconductor Lasers : Stability , Instability and Chaos , 2013 .

[19]  Mariia Sorokina,et al.  Fiber-Optic Reservoir Computing for QAM-Signal Processing , 2018, 2018 European Conference on Optical Communication (ECOC).

[20]  M. Eiselt,et al.  Evaluation of Real-Time 8 × 56.25 Gb/s (400G) PAM-4 for Inter-Data Center Application Over 80 km of SSMF at 1550 nm , 2017, Journal of Lightwave Technology.

[21]  Dan Sadot,et al.  Single channel 112Gbit/sec PAM4 at 56Gbaud with digital signal processing for data centers applications , 2015, OFC 2015.

[22]  Lin Sun,et al.  Nonlinear Distortion Mitigation by Machine Learning of SVM Classification for PAM-4 and PAM-8 Modulated Optical Interconnection , 2018, Journal of Lightwave Technology.

[23]  L. Appeltant,et al.  Information processing using a single dynamical node as complex system , 2011, Nature communications.

[24]  Chao Lu,et al.  Machine Learning Methods for Optical Communication Systems , 2017 .

[25]  Ingo Fischer,et al.  Photonic machine learning implementation for signal recovery in optical communications , 2018, Scientific Reports.

[26]  Daniel Brunner,et al.  Parallel photonic information processing at gigabyte per second data rates using transient states , 2013, Nature Communications.

[27]  Benjamin Schrauwen,et al.  Parallel Reservoir Computing Using Optical Amplifiers , 2011, IEEE Transactions on Neural Networks.

[28]  Michiel Hermans,et al.  Online Training of an Opto-Electronic Reservoir Computer Applied to Real-Time Channel Equalization , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[29]  Polina Bayvel,et al.  448-Gb/s PAM4 Transmission Over 300-km SMF-28 Without Dispersion Compensation Fiber , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[30]  D. Zibar,et al.  Machine Learning Techniques in Optical Communication , 2016 .

[31]  Winston I. Way,et al.  100-km DWDM Transmission of 56-Gb/s PAM4 per $\lambda $ via Tunable Laser and 10-Gb/s InP MZM , 2015, IEEE Photonics Technology Letters.

[32]  Andreas Leven,et al.  Applying Neural Networks in Optical Communication Systems: Possible Pitfalls , 2017, IEEE Photonics Technology Letters.

[33]  Sjoerd van der Heide,et al.  112-Gbit/s Single Side-Band PAM-4 Transmission over Inter-DCI Distances Without DCF Enabled by Low-complexity DSP , 2017, 2017 European Conference on Optical Communication (ECOC).

[34]  Weisheng Hu,et al.  56 Gbps IM/DD PON based on 10G-Class Optical Devices with 29 dB Loss Budget Enabled by Machine Learning , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[35]  Mariia Sorokina,et al.  Fiber echo state network analogue for high-bandwidth dual-quadrature signal processing. , 2019, Optics express.

[36]  Chen Chen,et al.  Transmission of 56-Gb/s PAM-4 over 26-km single mode fiber using maximum likelihood sequence estimation , 2015, 2015 Optical Fiber Communications Conference and Exhibition (OFC).